{"id":"W4318830209","doi":"10.3389/fgene.2022.900595","title":"Considering strategies for SNP selection in genetic and polygenic risk scores","year":2022,"lang":"en","type":"article","venue":"Frontiers in Genetics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Jewish General Hospital; University of Toronto; McGill University","funders":"National Institute of Dental and Craniofacial Research; National Institute of Neurological Disorders and Stroke; National Institute on Aging; Genome Canada; Canadian Institutes of Health Research; University at Buffalo; National Heart, Lung, and Blood Institute; McGill University; Natural Sciences and Engineering Research Council of Canada; Johns Hopkins University","keywords":"SNP; Polygenic risk score; Selection (genetic algorithm); Single-nucleotide polymorphism; Construct (python library); Contrast (vision); Biology; Genetics; Computer science; Machine learning; Genotype; Artificial intelligence; Gene","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1795446,0.0017386,0.002044716,0.002801059,0.001202323,0.006906555,0.003958046,0.004726637,0.002001155],"category_scores_gemma":[0.3843395,0.0007604539,0.002566249,0.002661442,0.008086078,0.005474114,0.003763493,0.008589057,0.0007351072],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00297473,"about_ca_system_score_gemma":0.003744698,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004711643,"about_ca_topic_score_gemma":0.006448576,"domain_scores_codex":[0.8183359,0.1557283,0.006505491,0.006599593,0.01173006,0.001100643],"domain_scores_gemma":[0.5971428,0.3688888,0.005753639,0.01106826,0.01593717,0.001209364],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005446019,0.00005320118,0.01421218,0.00116341,0.001915144,0.0004007918,0.002736106,0.05280983,0.0006215078,0.5389796,0.02258719,0.3639763],"study_design_scores_gemma":[0.0002024078,0.0002472861,0.003044986,0.001317087,0.0004295501,0.0003254096,0.0004877418,0.1074893,0.0009579575,0.8533169,0.03201406,0.0001672652],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01289993,0.01104303,0.8842185,0.08130863,0.003697574,0.000311702,0.0002191515,0.0003072218,0.005994283],"genre_scores_gemma":[0.2857635,0.005600312,0.6708574,0.02658644,0.00616915,0.0009184772,0.0001859276,0.0003710129,0.003547847],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1795446,"threshold_uncertainty_score":0.9495342,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01237599361674323,"score_gpt":0.2523358652606843,"score_spread":0.2399598716439411,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}